© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 3155
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to depression and emotional states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Libertad
    -0.57
    virt
    -0.52
     Mille
    -0.51
    posterous
    -0.49
    hausen
    -0.48
    Mille
    -0.48
     lcm
    -0.47
    udesta
    -0.46
     harmless
    -0.45
     Chrift
    -0.45
    POSITIVE LOGITS
     gloomy
    1.42
     somber
    1.37
     gloom
    1.27
     melancholy
    1.27
     depressing
    1.24
     sombre
    1.21
     melancho
    1.17
     mourning
    1.14
     mournful
    1.14
     dark
    1.12
    Activations Density 0.193%

    No Known Activations